Learning with low-rank approximations

Jérémy Cohen
IRISA, équipe PANAMA, CNRS, Rennes
https://scholar.google.fr/citations?user=MlBzHfcAAAAJ&hl=fr

Date(s) : 25/06/2021   iCal
14 h 30 min - 15 h 30 min

Matrix and tensor factorizations are widespread techniques to blindly extract structure out of data. Research on tensor methods is rapidly growing and encompases many aspect of computer science such as high performance computing and large scale non-convex optimization. An important challenge is to propose or study matrix and tensor models which are of practical interest while making efficient use of recent developements in both low-level tensor computation techniques such as tensor contractions on GPUs and large-scale non-convex optimization techniques such as stochastic gradient algorithms and proximal algorithms. After introducing low-rank approximation methods and depicting the current research landscape, I will focus on two recent contributions: (i) Unsupervised music automatic segmentation using nonnegative Tucker decomposition (ii) Heuristic extrapolated block-coordinate descent algorithm for tensor decompositions.

This seminar will be online, please contact the organisers if you wish to attend (https://listes.math.cnrs.fr/wws/info/sem-signal-apprentissage).

Catégories



Retour en haut